From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1030319AbbCMPQ1 (ORCPT ); Fri, 13 Mar 2015 11:16:27 -0400 Received: from smtprelay0010.hostedemail.com ([216.40.44.10]:46181 "EHLO smtprelay.hostedemail.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S932194AbbCMPPX (ORCPT ); Fri, 13 Mar 2015 11:15:23 -0400 X-Session-Marker: 6E657665747340676F6F646D69732E6F7267 X-Spam-Summary: 2,0,0,,d41d8cd98f00b204,,::::::::::::::::::::::::,RULES_HIT:355:379:871:988:989:1183:1260:1277:1312:1313:1314:1345:1516:1518:1519:1522:1534:1593:1594:1595:1596:1692:1730:1747:1777:1792:2392:2393:2559:2562:2828:3138:3139:3140:3141:3142:3876:3877:5007:6114:6261:6642:6748:7281:7901:9012:10004:10848:11604:11914:12517:12519:13895:14394:21080,0,RBL:none,CacheIP:none,Bayesian:0.5,0.5,0.5,Netcheck:none,DomainCache:0,MSF:not bulk,SPF:fn,MSBL:0,DNSBL:none,Custom_rules:0:0:0 X-HE-Tag: snow51_68d1ed043ad59 X-Filterd-Recvd-Size: 3550 Message-Id: <20150313151519.716061711@goodmis.org> User-Agent: quilt/0.61-1 Date: Fri, 13 Mar 2015 11:15:22 -0400 From: Steven Rostedt To: linux-kernel@vger.kernel.org, linux-rt-users Cc: Thomas Gleixner , Carsten Emde , Sebastian Andrzej Siewior , John Kacur , Paul Gortmaker , "Paul E. McKenney" , Josh Triplett , Peter Zijlstra , Oleg Nesterov , Mike Galbraith Subject: [PATCH RT 28/31] timers: Reduce __run_timers() latency for empty list References: <20150313151454.809081378@goodmis.org> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Disposition: inline; filename=0028-timers-Reduce-__run_timers-latency-for-empty-list.patch Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.10.70-rt75-rc1 stable review patch. If anyone has any objections, please let me know. ------------------ From: "Paul E. McKenney" upstream commit: d550e81dc0ddc04f1b417c179c214103a28e0ee8 The __run_timers() function currently steps through the list one jiffy at a time in order to update the timer wheel. However, if the timer wheel is empty, no adjustment is needed other than updating ->timer_jiffies. In this case, which is likely to be common for NO_HZ_FULL kernels, the kernel currently incurs a large latency for no good reason. This commit therefore short-circuits this case. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett Acked-by: Peter Zijlstra Reviewed-by: Oleg Nesterov Reviewed-by: Steven Rostedt Tested-by: Mike Galbraith Signed-off-by: Steven Rostedt --- kernel/timer.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/kernel/timer.c b/kernel/timer.c index 23919c7c212f..c20bd12a4f06 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -341,6 +341,20 @@ void set_timer_slack(struct timer_list *timer, int slack_hz) } EXPORT_SYMBOL_GPL(set_timer_slack); +/* + * If the list is empty, catch up ->timer_jiffies to the current time. + * The caller must hold the tvec_base lock. Returns true if the list + * was empty and therefore ->timer_jiffies was updated. + */ +static bool catchup_timer_jiffies(struct tvec_base *base) +{ + if (!base->all_timers) { + base->timer_jiffies = jiffies; + return true; + } + return false; +} + static void __internal_add_timer(struct tvec_base *base, struct timer_list *timer) { @@ -1203,6 +1217,10 @@ static inline void __run_timers(struct tvec_base *base) struct timer_list *timer; spin_lock_irq(&base->lock); + if (catchup_timer_jiffies(base)) { + spin_unlock_irq(&base->lock); + return; + } while (time_after_eq(jiffies, base->timer_jiffies)) { struct list_head work_list; struct list_head *head = &work_list; -- 2.1.4